{"mean_reward": 646.0, "std_reward": 256.0058593079463, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-11-14T08:40:18.303944"} |
{"mean_reward": 646.0, "std_reward": 256.0058593079463, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-11-14T08:40:18.303944"} |